Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    first-person possessive pronouns and possessive determiners

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and phrases indicating personal responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dates
    -0.75
    orks
    -0.69
     Figures
    -0.66
    clips
    -0.66
    aucus
    -0.65
    groups
    -0.63
    roup
    -0.61
    APD
    -0.61
     existed
    -0.61
     exists
    -0.61
    POSITIVE LOGITS
     fault
    1.19
     favorite
    1.19
     favourite
    1.14
     own
    1.09
     consolation
    1.06
     livelihood
    1.00
    cule
    0.96
     intention
    0.95
     salvation
    0.94
     downfall
    0.94
    Act Density 0.135%

    No Known Activations